© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 23881
    Prev
    Next
    INDEX
    Explanations

    class destructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     because
    -1.55
    。』
    -1.52
    *}$
    -1.52
     some
    -1.52
    ｼ
    -1.44
     mouseClicked
    -1.40
    というのも
    -1.38
    *
    -1.38
     contains
    -1.38
     You
    -1.38
    POSITIVE LOGITS
     of
    1.72
     provincie
    1.53
    蔟
    1.48
     vitale
    1.44
    denken
    1.44
     fiscale
    1.43
     collega
    1.42
     intelligente
    1.41
     mutta
    1.41
     leden
    1.41
    Activations Density 0.005%

    No Known Activations